def _get_feat(self, db, f_class):
if f_class == 'color':
f_c = Color()
elif f_class == 'daisy':
f_c = Daisy()
elif f_class == 'edge':
f_c = Edge()
return f_c.make_samples(db, verbose=False)
def method_select(name):
if name == "color":
ret = Color()
elif name == "edge":
ret = Edge()
elif name == "gabor":
ret = Gabor()
elif name == "daisy":
ret = Daisy()
elif name == "HOG":
ret = HOG()
return ret
def _get_feat(self, db, f_class):
if f_class == 'color':
f_c = Color()
elif f_class == 'daisy':
f_c = Daisy()
elif f_class == 'edge':
f_c = Edge()
elif f_class == 'gabor':
f_c = Gabor()
elif f_class == 'hog':
f_c = HOG()
elif f_class == 'vgg':
f_c = VGGNetFeat()
elif f_class == 'res':
f_c = ResNetFeat()
return f_c.make_samples(db, verbose=False)
def __init__(self, db, f_class=None, d_type='L1'):
self.NGT_dir = 'NGT_{}_{}'.format(f_class,d_type)
self.NGT_path = b''
self.fearure = f_class
self.SQLdb = SQLite()
if f_class == 'daisy':
self.f_c = Daisy()
self.NGT_path = b'NGT/NGT_daisy_'+d_type.encode()
elif f_class == 'edge':
self.f_c = Edge()
self.NGT_path = b'NGT/NGT_edge_'+d_type.encode()
elif f_class == 'hog':
self.f_c = HOG()
self.NGT_path = b'NGT/NGT_hog_'+d_type.encode()
elif f_class == 'vgg':
self.f_c = VGGNetFeat()
self.NGT_path = b'NGT/NGT_vgg_'+d_type.encode()
elif f_class == 'res':
self.f_c = ResNetFeat()
self.NGT_path = b'NGT/NGT_res_'+d_type.encode()
if not os.path.exists(os.path.join(NGT_dir,self.NGT_dir)):
samples = self.f_c.make_samples(db, verbose=False)
dim = 0
try:
dim = samples[0]['hist'].shape[0]
except:
pass
images= []
objects = []
for i, row in enumerate(samples):
vector = row['hist']
link = row['img']
lable = row['cls']
data = {'index':i,'link':link,'lable':lable}
images.append(data)
objects.append(vector)
self.SQLdb.updateMuti(f_class,images)
# cPickle.dump(images, open(os.path.join(NGT_dir, sample_cache), "wb", True))
ngtpy.create(path=self.NGT_path, dimension=dim, distance_type=d_type)
self.index = ngtpy.Index(self.NGT_path)
self.index.batch_insert(objects)
self.index.save()
self.index = ngtpy.Index(self.NGT_path)
depth = 5
d_type = 'd1'
query_idx = 0
if __name__ == '__main__':
db = Database()
# retrieve by color
method = Color()
samples = method.make_samples(db)
query = samples[query_idx]
_, result = infer(query, samples=samples, depth=depth, d_type=d_type)
print(result)
# retrieve by daisy
method = Daisy()
samples = method.make_samples(db)
query = samples[query_idx]
_, result = infer(query, samples=samples, depth=depth, d_type=d_type)
print(result)
# retrieve by edge
method = Edge()
samples = method.make_samples(db)
query = samples[query_idx]
_, result = infer(query, samples=samples, depth=depth, d_type=d_type)
print(result)
# retrieve by gabor
method = Gabor()
samples = method.make_samples(db)
A_types = np.array([c.A_w, c.A_b])
h = 0.1
dL = 0.01
Ls = np.arange(0.6, 1.6 + dL, dL)
N = len(Ls)
pops = np.zeros((N, len(a_types)))
Ts = np.zeros_like(Ls)
pops[0] = np.zeros_like(a_types) + 0.01
for i, L in enumerate(Ls[:-1]):
# Initial guess is last step
a_0 = np.where(pops[i] < 0.01, 0.01, pops[i])
# Make new daisy object for this solution
d_cur = Daisy(1, 0.3, a_0, A_types, L)
# Solve
d_cur.rk4Solve(100000, h)
pops[i + 1] = d_cur.a_vec[:-1]
Ts[i + 1] = d_cur.Teff
print(f'L = {L:1.1f}', end=' || ')
for i, p in enumerate(pops[i + 1]):
print(f'p_{i} = {p:1.2e}', end=' || ')
print(f'total = {np.sum(pops[i+1, :]):1.2e}', end='\n')
fig, axes = plt.subplots(2, 1)
ax = axes.flatten()[0]
ax.plot(Ls, pops[:, 0] * 100, 'b-', label='White daisy fraction')
ax.plot(Ls, pops[:, 1] * 100, 'k-', label='Black daisy fraction')
depth = 100
d_type = 'd1'
query_idx = 3
if __name__ == '__main__':
db = Database()
# # retrieve by color
# method = Color()
# samples = method.make_samples(db)
# query = samples[query_idx]
# _, result = infer(query, samples=samples, depth=depth, d_type=d_type)
# print(result)
# retrieve by daisy
method = Daisy()
samples = method.make_samples(db)
query = samples[query_idx]
_, result = infer(query, samples=samples, depth=depth, d_type=d_type)
print(result)
# retrieve by edge
method = Edge()
samples = method.make_samples(db)
query = samples[query_idx]
_, result = infer(query, samples=samples, depth=depth, d_type=d_type)
print(result)
# # retrieve by gabor
# method = Gabor()
# samples = method.make_samples(db)
def _get_feat(self, db, f_class, sample_name=""):
if f_class == 'color':
f_c = Color()
elif f_class == 'daisy':
f_c = Daisy()
return f_c.make_samples(db, verbose=False, sample_name=sample_name)
"""
try:
name, weight = s.split(':')
weight = int(weight)
if name not in features.keys() or weight < 1:
raise Exception
return name, weight
except:
raise argparse.ArgumentTypeError(
f"\nFeature must be 'name:weight'\n\tname in {features.keys()}\n\tweight >= 1"
)
features = {
"color": Color(),
"daisy": Daisy(),
"edge": Edge(),
"gabor": Gabor(),
"hog": HOG(),
"vgg": VGGNetFeat(),
"res": ResNetFeat(),
}
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("-n",
"--neighbor",
help="neighbor by class",
type=int,
default=3)
parser.add_argument(